This thesis advances the computational understanding and manipulation of text styles through three interconnected pillars: (1) Text Style Transfer (TST), which alters stylistic properties (e.g., sentiment, formality) while preserving content; (2)Authorship Attribution (AA), identifying the author of a text via stylistic fingerprints; and (3) Authorship Verification (AV), determining whether two texts share the same authorship. We address critical challenges in these areas by leveraging parameter-efficient adaptation of large language models (LLMs), contrastive disentanglement of stylistic features, and instruction-based fine-tuning for explainable verification.
@article{arxiv.2507.16530,
title = {Learning Text Styles: A Study on Transfer, Attribution, and Verification},
author = {Zhiqiang Hu},
journal= {arXiv preprint arXiv:2507.16530},
year = {2025}
}